More Like this

1. Optimal Operations Management of Mobility-on-Demand Systems

   https://doi.org/10.3389/frsc.2021.681096  

   Wollenstein-Betech, Salomón; Paschalidis, Ioannis Ch.; Cassandras, Christos G. (July 2021, Frontiers in Sustainable Cities)

   null (Ed.)

   The emergence of the sharing economy in urban transportation networks has enabled new fast, convenient and accessible mobility services referred to as Mobilty-on-Demand systems (e.g., Uber, Lyft, DiDi). These platforms have flourished in the last decade around the globe and face many operational challenges in order to be competitive and provide good quality of service. A crucial step in the effective operation of these systems is to reduce customers' waiting time while properly selecting the optimal fleet size and pricing policy. In this paper, we jointly tackle three operational decisions: (i) fleet size, (ii) pricing, and (iii) rebalancing, in order to maximize the platform's profit or its customers' welfare. To accomplish this, we first devise an optimization framework which gives rise to a static policy. Then, we elaborate and propose dynamic policies that are more responsive to perturbations such as unexpected increases in demand. We test this framework in a simulation environment using three case studies and leveraging traffic flow and taxi data from Eastern Massachusetts, New York City, and Chicago. Our results show that solving the problem jointly could increase profits between 1% and up to 50%, depending on the benchmark. Moreover, we observe that the proposed fleet size yield utilization of the vehicles in the fleet is around 75% compared to private vehicle utilization of 5%. 

   more » « less
2. Graph Meta-Reinforcement Learning for Transferable Autonomous Mobility-on-Demand

   https://doi.org/10.1145/3534678.3539180  

   Gammelli, Daniele; Yang, Kaidi; Harrison, James; Rodrigues, Filipe; Pereira, Francisco; Pavone, Marco (August 2022, Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining)

   Autonomous Mobility-on-Demand (AMoD) systems represent an attractive alternative to existing transportation paradigms, currently challenged by urbanization and increasing travel needs. By centrally controlling a fleet of self-driving vehicles, these systems provide mobility service to customers and are currently starting to be deployed in a number of cities around the world. Current learning-based approaches for controlling AMoD systems are limited to the single-city scenario, whereby the service operator is allowed to take an unlimited amount of operational decisions within the same transportation system. However, real-world system operators can hardly afford to fully re-train AMoD controllers for every city they operate in, as this could result in a high number of poor-quality decisions during training, making the single-city strategy a potentially impractical solution. To address these limitations, we propose to formalize the multi-city AMoD problem through the lens of meta-reinforcement learning (meta-RL) and devise an actor-critic algorithm based on recurrent graph neural networks. In our approach, AMoD controllers are explicitly trained such that a small amount of experience within a new city will produce good system performance. Empirically, we show how control policies learned through meta-RL are able to achieve near-optimal performance on unseen cities by learning rapidly adaptable policies, thus making them more robust not only to novel environments, but also to distribution shifts common in real-world operations, such as special events, unexpected congestion, and dynamic pricing schemes. 

   more » « less
3. A simulation‐based optimization model for infrastructure planning for electric autonomous vehicle sharing

   https://doi.org/10.1111/mice.12506  

   Zhao, Dongfang; Li, Xiaopeng; Cui, Jianxun (November 2019, Computer-Aided Civil and Infrastructure Engineering)

   Abstract New transportation technologies (e.g., electric autonomous vehicles [EAVs]) and operation paradigms (e.g., car sharing) are discussed, researched, and to a small degree also deployed in recent years in response to rising energy crises and aggravating traffic congestions. In this research, we present a station‐based car‐sharing service system that integrates both EAV technologies and car‐sharing operations. Based on the simulation model, a dynamic and time‐continuous optimization model seeking a near‐optimum design of charging station location and EAV deployment is developed. By discretizing the model, we proposed a Monte Carlo simulation model to evaluate the total system cost for a given location and vehicle deployment design. A heuristic approach based on the genetic algorithm is developed to solve the system design of station location and vehicle deployment. A numerical test in Yantai City, China, is conducted to illustrate the effectiveness of the proposed model and to draw managerial insights into how the key parameters affect the system design. 

   more » « less
4. Examining User Access Options for eGovernment Services During a Crisis from a Digital Inequality Perspective

   Zobel, C.W.; Pamukcu, D. (January 2023, Proceedings of the 56th Hawaii International Conference on System Sciences)

   City governments incorporate ICTs into government services to improve citizen participation and access to those services. Too much dependence on technology, however, can lead to concerns about creating a digital divide between different groups of citizens. The potential for digital inequality is a critical issue that can be exacerbated by insufficient attention being paid to vulnerabilities across communities. Given that socio-economically vulnerable populations are the ones who need government services the most, especially during disaster events, it is critical to investigate the extent to which digital inequality is an issue for technology-based government services. With this in mind, this paper analyzes the use of different technology-enabled access options for a representative eGovernment service system, the New York City 311 service system, in the early stages of the COVID-19 pandemic. Two sets of socio-economically distinct locations in New York City are compared, using average income as a proxy for vulnerability, to draw conclusions about potential inequalities in such a system during a crisis. 

   more » « less
5. The Anatomy of the Daily Usage of Bike Sharing Systems:Elevation, Distance and Seasonality

   Injung Kim, Konstantinos Pelechrinis (July 2020, ACM SIGKDD workshop on Urban Computing)

   null (Ed.)

   Bike sharing systems have been in place for several years in many urban areas as alternative and sustainable means of transportation. Bicycle usage heavily depends on the available infrastructure (e.g., protected bike lanes), but other—mutable or immutable—environmental characteristics of a city can influence the adoption of the system from its dwellers. Hence, it is important to understand how these factors influence people’s decisions of whether to use a bike system or not. In this this paper, we first investigate how altitude variation influences the usage of the bike sharing system in Pittsburgh. Using trip data from the system, and controlling fora number of other potential confounding factors, we formulate the problem as a classification problem, develop a framework to enable prediction using Poisson regression, and find that there is a negative correlation between the altitude difference and the number of trips between two stations (fewer trips between stations with larger altitude difference). We further, discuss how the results of our analysis can be used to inform decision making during the design and operation of bike sharing systems. 

   more » « less